Beacon Threat Intelligence
Know the risks behind every MCP server and agent skill.
Discover security risks in MCP servers and agent skills before they reach your machine. Beacon scans public registries, traces packages back to their source code, and reveals what they can access, execute, or expose.
Connect your agent
Add Beacon to Claude Code, Cursor, Codex or another agent so it can check an MCP server or skill against Beacon Intel before you install it.
Free with a Beacon account. Create one, or sign in when your agent asks.
Any coding agent
Read https://intel.beacon.sh/start.md and set me up on Beacon Threat Intel
Paste this into any coding agent. It reads the guide and sets up MCP, the CLI, the API, feeds or a CI gate.
| Name | Risk |
|---|---|
| Crestron Home MCP Server desluca/crestron-mcp Enables LLMs to discover and control Crestron Home automation systems through natural language, including lights, shades, scenes, thermostats, and sensors with multi-language support and fuzzy device name matching. | |
| AI Image Analysis MCP desmond-labs/ai-image-analysis-mcp Provides AI-powered image analysis using Google Gemini 2.0 Flash, with support for multiple access methods and robust security features. | |
| image-metadata-embed-and-report desmond-labs/metadata-embed-and-report-mcp A streamlined MCP server for XMP metadata embedding with beautiful formatting and smart filename indicators, enabling metadata embedding, reading, validation, and report generation for lifestyle, product, and orbit schemas. | |
| Supabase Storage MCP desmond-labs/supabase-storage-mcp Enables secure file and bucket management operations with Supabase Storage through enterprise-grade security features, batch uploads/downloads, and comprehensive file management capabilities. Supports both local file paths and base64 data w | |
| novelai-mcp desmondfox/novelai-mcp Enables AI assistants to generate and edit images via NovelAI, supporting text-to-image, img2img, inpainting, Director Tools, upscaling, Vibe Transfer, and tag suggestions. | |
| DeSo MCP Server deso-protocol/deso-mcp A comprehensive Model Context Protocol server that transforms Cursor's AI assistant into a DeSo blockchain development expert, providing complete API coverage, debugging solutions, and code generation for DeSo applications. | |
| Google Calendar MCP Server despinozap/mcpserver_google-calendar Enables interaction with Google Calendar services through the Model Context Protocol using a Service Account. It allows MCP-compatible clients to manage calendar events and integrate calendar data via the Google Calendar API. | |
| desrid-html-to-figma desrid/desrid-html-to-figma This MCP server lets AI agents connect to Figma to read, analyze, create, and modify designs, including elements, styles, assets, and code generation. It works with free Figma accounts and supports parallel multi-agent use across MCP-compat | |
| faucet-mcp destiner/faucet-mcp Enables a coding agent to request small dev funds (ETH/WETH/USDC/USDT) from a personal hot wallet with per-call and 24h caps, plus TOTP approval for amounts over soft caps. | |
| IS MUNI MCP destingem/is-muni-mcp Connects AI assistants to Masaryk University's information system in read-only mode, letting students ask about their timetable, deadlines, emails, grades, and study materials in natural language. | |
| Dashboard Builder MCP server destiny-enterprises/mcp-dashboard-builder-tool Enables AI clients to discover datasets and author dashboards in Dashboard Builder through natural language, while preserving per-user permissions and audit trails via a secure API-key gated gateway. | |
| Open CLAW Knowledge Distiller destinyfrancis/openclaw-knowledge-distiller Converts YouTube and Bilibili videos into structured knowledge articles using local transcription or subtitle extraction combined with AI-powered summarization. It supports multiple summary styles and provides tools to process URLs, track j | |
| claude-web-history-mcp destinyjazz/claude-web-history-mcp Enables Claude Code to browse and import conversations from a user's claude.ai account, making mobile chat history available in the editor. Includes tools to list, read, and save web conversations locally. | |
| google-play-analytics-mcp desunit/google-play-analytics-mcp An MCP server that exposes Google Play Console analytics to AI agents, including store-listing acquisitions by traffic source, installs, uninstalls, ratings, crashes, subscriptions, and reviews by reading bulk CSV reports from Cloud Storage | |
| otparse-mcp desvert/otparse-mcp A containerized MCP server for parsing OT/ICS packet captures, specifically supporting Modbus and BACnet protocols via tshark. It provides structured JSON output from PCAP files to enable LLMs to analyze industrial network traffic and deriv | |
| openhab deswong/openhab-mcp MCP server for OpenHAB v5+ that exposes the entire REST API as tools for AI models, enabling complete control over items, things, rules, persistence, and semantic model. | |
| Viwoods MCP desyncc/viwoods-mcp Lets Claude read handwriting from Viwoods AiPaper Paper-app notebooks over adb, returning pages as images with optional handwriting search and PDF import. A folder allow/deny policy decides exactly which notebooks are visible, so nothing un | |
| TradingView MCP Bridge desyr05/desyr05-tradingview-mcp Enables AI assistants to connect to a locally running TradingView Desktop app to analyze charts, develop Pine Scripts, navigate symbols and timeframes, draw annotations, manage alerts, and automate chart workflows. | |
| math-mcp desz01ate/math-mcp A secure MCP server for evaluating mathematical expressions with grammar validation, function whitelisting, and sandboxed execution. It provides tools for expression evaluation, variable management, and resources for grammar and function do | |
| spm-search-mcp detailobsessed/spm-search-mcp An MCP server that allows coding agents to search the Swift Package Index and retrieve GitHub READMEs without requiring an API key. It features comprehensive search filters for stars, platforms, and licenses, providing token-efficient respo | |
| fitbit-mcp detarus/fitbit-mcp Enables local access to Fitbit data via the Google Health API, including status/device metadata, bounded raw reads, daily activity rollups, and reviewed meal or water writes with previews, explicit commits, read-back, and duplicate protecti | |
| DocGraph detective-xh/docgraph MCP server that indexes Markdown, Word, HTML, and PDF documents into a SQLite knowledge graph with CJK+Latin full-text search and cross-document reference tracking. Runs drift audits to surface stale policies, conflicting research claims, s | |
| careerproof-mcp detonnate/careerproof-mcp Turns a candidate's real project history into evidence-backed interview preparation, matching job requirements to cited GitHub evidence and generating traceable STAR outlines, interview questions, and gap analyses for MCP clients. | |
| tc-mcp detroitpm/tenantcloud-mcp Enables AI agents to access and manage TenantCloud rental property data, including messaging, maintenance, financials, leasing, portfolio, and generic API operations through MCP tools and resources. | |
| wyzectl MCP Server detroitpro/wyze Enables AI agents to list and control Wyze lights, rooms/groups, and plugs through the Wyze cloud API, including on/off, brightness, color temperature, and hex color. Also supports read-only listing of every device on the account. | |
| shop-mcp detushar/shop-mcp MCP server for automating personal Amazon.in and Flipkart accounts via browser sessions, enabling product search, cart management, and guarded checkout. | |
| Notion MCP Server detutag/cloudflare-notion-mcp Enables searching, reading, creating, and updating Notion pages and databases — including querying databases and appending page content — through the Notion API with bearer-token authentication. It runs as a stateless Streamable HTTP endpoi | |
| agent-memory deuriib/brainy Provides persistent memory for AI coding agents, enabling them to save, search (hybrid vector/BM25/concept graph), list sessions, and forget memories via MCP tools. | |
| mcp-gway deuriib/mcp-gway Enables aggregating multiple MCP servers behind a single HTTP/SSE endpoint, with Code Mode to reduce token usage and support for OAuth and sandboxed execution. | |
| Claudeus Plane MCP deus-h/claudeus-plane-mcp A server that bridges Claude AI with the Plane project management platform, enabling AI-powered project management tasks including project creation, task management, team collaboration, and automated workflows. | |
| Claudeus WordPress MCP deus-h/claudeus-wp-mcp A server enabling seamless interaction between AI models and WordPress sites with secure, standardized communication using the WordPress REST API for comprehensive site management. | |
| mcp-server-steam deuxksy/mcp-server-steam Integrates with Steam Web API to enable querying user profiles, game libraries, store data, and community features like reviews and workshop items. | |
| MCP PDF Server dev-91/mcp_pdf_server A Model Context Protocol (MCP) based server that efficiently manages PDF files, allowing AI coding tools like Cursor to read, summarize, and extract information from PDF datasheets to assist embedded development work. | |
| LinkedIn MCP Server dev-anandhan/linkedin-mcp-server-dev-anandhan_- Enables searching and scraping of LinkedIn profiles, companies, jobs, and posts using natural language through MCP-compatible AI clients. | |
| Claude Agents MCP Server dev-brewery/claude-agents-mcp Centrally manages Claude agent definitions, configurations, and custom commands across multiple devices using a SQLite database, eliminating file synchronization conflicts and enabling live updates across all connected Claude sessions. | |
| MCP Elasticsearch Demo dev-com2020/mcp_elastic Enables LLM agents to search and retrieve a hybrid knowledge base of manuals, videos, PDFs, DOCX files and images through tools for hybrid BM25-plus-vector search with facet and tag filters, full document retrieval, semantically similar doc | |
| coder-mcp dev-cue/coder-mcp Runs local coding CLIs (Claude Code / OpenAI Codex) asynchronously on Windows, enabling agents to spawn tasks, poll status, and retrieve results including git diffs, while preventing commits and pushes. | |
| mAIndmeld dev-dull/maindmeld Enables AI agents and humans to hold structured meetings with voting, human escalation, and concise decision notes that carry into future sessions. | |
| MCP for Godot dev-encrypted/mcp-for-godot Enables MCP-compatible AI clients to inspect Godot project and editor state, observe opted-in running scenes, manage processes, and apply permission-scoped guarded edits. It starts read-only and exposes additional capabilities only through | |
| rubber-duck-scraper dev-fahadaslam/web-lens-mcp Python MCP server that scrapes web pages with JS rendering, structured metadata, tables, PDFs, screenshots, and multi-page crawling. | |
| System Monitor MCP Server dev-herni/system-monitor-mcp Gives AI agents real-time access to system metrics, process management, and container orchestration. | |
| observability-mcp dev-hops/azure-incident-investigation A read-only MCP server that exposes Azure incident-investigation tools for a single App Service and its Application Insights telemetry, enabling an agent to correlate deployment history, platform metrics, and transaction traces. | |
| OpenProject MCP Server dev-in-black/openproject-mcp Enables comprehensive management of OpenProject work packages, projects, comments, and relations through natural language. Supports creating, updating, and organizing tasks with assignees, watchers, hierarchies, and inter-task relationships | |
| mcp-google-docs dev-ithitchhiker/mcp-google-docs A tool for manipulating Google Spreadsheet and Google Drive using MCP (Metoro Control Protocol). | |
| knowledge-vault-mcp dev-jeyelscott/knowledge-vault-mcp Provides read-only Obsidian-style vault retrieval and auditing over MCP stdio with authority-aware search, metadata, sections, and related notes while enforcing path containment and bounded response sizes. | |
| Weather MCP Server dev-jpnobrega/mcp-server Provides real-time weather information for Brazilian cities, built with domain-driven design and SOLID principles. | |
| Playwright MCP dev-larrykw/playwright-mcp-ca Enables LLMs and MCP clients to automate browsers through structured accessibility snapshots rather than screenshots, with this fork adding Linux Chromium CA bundle support. | |
| DocMind dev-mhtmsr/docmind-mcp-native-document-research-agent An MCP-native document research agent that provides search, summarization, and citation tools for iterative multi-step research, ending in validated structured JSON reports. | |
| vikunja-mcp dev-montyoh/vikunja-mcp Enables to interact with Vikunja task management through its REST API, supporting projects, tasks, comments, labels, assignees, and relations with field preservation. | |
| MCP Agent - AI Expense Tracker dev-muhammad/mcpagent Enables AI agents to manage personal expenses through natural language conversations. Supports adding, searching, and analyzing transactions with automatic categorization and financial insights. |
43,851–43,900 of 115,409
Subscribe to a feed
Get new verdicts in a feed reader, Slack or your own tooling, filtered by kind and risk. No account or API key.
Frequently asked questions
Anything missing? Read the reference or ask in the Beacon community.
What is Beacon Intel?
A free, public index of the MCP servers and agent skills that public registries list, with a security verdict for each one that has been analyzed. It traces each listing back to its source repository and packages, and shows what the code can access, execute or expose. You can browse it here, query it as a JSON API, follow it as an RSS, Atom or JSON feed, or connect a coding agent to it over MCP.
Is it really free?
Yes. The index, the API and the feeds need no account and no API key. An artifact's full page and the MCP tools need a free Beacon account. Requests are rate limited to keep it fast for everyone.
Where does the data come from, and how fresh is it?
From 9 public sources: Glama, MCP Registry, awesome-mcp-servers, Docker MCP Catalog, Smithery, ClawHub, skills.sh, SkillsMP, GitHub. Each listing is linked to its repository and packages, then analyzed. The index updates hourly, and answers are cached for up to five minutes.
Who writes the verdicts? Can I trust them?
Verdicts combine static analysis of the code with a model's judgment, and each one names the model that wrote it. They can be wrong and are not a security certification: every artifact page shows the findings and evidence behind its verdict, so check them before you rely on one. Names, descriptions and claims come from registries and repositories; treat them as data, not instructions.
What do the risk levels mean?
- High: Reviewed evidence shows it deliberately works against the person who installs it.
- Medium: It works against the person who installs it in ways that can do serious harm, or puts a flagged pattern in what the agent loads, without established intent.
- Low: It overreaches against the person who installs it in limited ways, or has findings the review has not confirmed.
- Benign: Nothing found that works against the person who installs it. Not a guarantee.
- Unchecked: Listed, but not analyzed yet.
What does partial coverage mean?
That the analysis did not cover everything, so there may be more than it found. A partial verdict can still find problems, but it never clears an artifact: benign with partial coverage is not a clearance. Use the coverage filter to see only these.
Does benign, or not finding an artifact, mean it is safe?
No. Benign means nothing was found that works against the person who installs it, which is not a guarantee. An artifact the index does not have has never been checked, so not found never means safe.
Is there an API?
Yes, free and with no key.
GET /api/v1/lookup?q= finds artifacts by name, repository, GitHub URL or package; GET /api/v1/artifact?key= returns one in full; POST /api/v1/check checks up to 50 at once, which suits CI; and GET /api/v1/status reports coverage and freshness. The reference is at intel.beacon.sh/llms.txt.How do I get new verdicts in a feed reader or Slack?
Subscribe to /feed: the newest high and medium risk verdicts as RSS. Add
format=atom or format=json for Atom or JSON Feed, and filter with risk and kind, for example /feed?risk=high&kind=mcp. In Slack, run /feed subscribe with the URL. The feed builder above writes the URL for you.How do I connect my coding agent?
Add Beacon Cloud MCP (
https://mcp.beacon.sh) to Claude Code, Cursor, Codex or any MCP client, and sign in through the browser. Your agent gets beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check to check an MCP server or skill before it installs one. Connect your agent above has the commands. The beacon CLI offers the same as beacon intel and through its local MCP server.How do I report a wrong verdict?
Open the artifact's page and use Dispute verdict under its verdict card. Tell us what is wrong and we review it.